Model Providers

Kurahi can use many LLM providers. Pick a provider, authenticate, then set the default model as provider/model.

Looking for chat channel docs (WhatsApp/Telegram/Discord/Slack/Mattermost (plugin)/etc.)? See Channels.

Default for evaluations: Sakura AI Engine

Japan-hosted, OpenAI-compatible, with a free tier of 3,000 chat requests a month. kurahi init offers it first.

• Default: sakura/gpt-oss-120b
• Also in the preset: sakura/llm-jp-3.1-8x13b-instruct, sakura/Kimi-K2.6 (public preview)

See Sakura AI Engine (日本語: さくらのAI Engine).

Quick start

1. Authenticate with the provider (kurahi init on a new installation, kurahi onboard later).
2. Set the default model:

{
  agents: { defaults: { model: { primary: "sakura/gpt-oss-120b" } } },
}

Provider docs

• Sakura AI Engine
• OpenAI (API + Codex)
• Anthropic (API + Claude Code CLI)
• OpenRouter
• Vercel AI Gateway
• Moonshot AI (Kimi + Kimi Coding)
• OpenCode Zen
• Amazon Bedrock
• Z.AI
• Xiaomi
• GLM models
• MiniMax
• Venice (Venice AI, privacy-focused)
• Ollama (local models)

Transcription providers

• Deepgram (audio transcription)

Community tools

• Claude Max API Proxy - Use Claude Max/Pro subscription as an OpenAI-compatible API endpoint

For the full provider catalog (xAI, Groq, Mistral, etc.) and advanced configuration, see Model providers.